ns ranging from biomass and product titer prediction to the estimation of biological state variables ( Choudhary and Kaur, 2025).
To overcome data availability limitations in non-linear bioprocesses, Gompertz functions have emerged as a valuable source of high-precision virtual data to train robust AI models. Moya-Almeida et al. (2021) demonstrated that combining Gompertz functions with artificial neural networks (ANN) enables accurate modeling and prediction of solvents produced by S. cerevisiae, addressing data scarcity and enhancing soft sensor reliability ( Moya-Almeida et al., 2021). Thes